Skip to content

feat: Increase LLM retry attempts and delays for enhanced robustness with complex agents. #147

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
tan-huynh wants to merge 2 commits into
base: main
Choose a base branch
from
+9 −4
Open

feat: Increase LLM retry attempts and delays for enhanced robustness with complex agents. #147

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b493b94
feat: Increase LLM retry attempts and delays for enhanced robustness …
tan-huynh Jan 18, 2026
b66ddd0
feat: Add `api_version` parameter to `MaterialOrganizerAgent` and sen…
tan-huynh Jan 18, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions src/agents/ideagen/material_organizer_agent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,13 +25,15 @@ def __init__(
language: str = "en",
api_key: str | None = None,
base_url: str | None = None,
api_version: str | None = None,
model: str | None = None,
):
super().__init__(
module_name="ideagen",
agent_name="material_organizer",
api_key=api_key,
base_url=base_url,
api_version=api_version,
model=model,
language=language,
)
Expand Down
3 changes: 3 additions & 0 deletions src/api/routers/ideagen.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -412,6 +412,9 @@ async def websocket_ideagen(websocket: WebSocket):
task_manager.update_task_status(task_id, "error", error=str(e))

try:
# Send explicit error message for consistency and better frontend handling
await websocket.send_json({"type": "error", "content": str(e)})

await send_status(
websocket,
IdeaGenStage.ERROR,
Expand Down
8 changes: 4 additions & 4 deletions src/services/llm/factory.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,8 +52,8 @@
logger = get_logger("LLMFactory")

# Default retry configuration
DEFAULT_MAX_RETRIES = 3
DEFAULT_RETRY_DELAY = 1.0 # seconds
DEFAULT_MAX_RETRIES = 5 # Increased for complex agents like Research
DEFAULT_RETRY_DELAY = 2.0 # seconds
DEFAULT_EXPONENTIAL_BACKOFF = True


Expand Down Expand Up @@ -197,8 +197,8 @@ def _is_retriable_llm_api_error(exc: BaseException) -> bool:
| tenacity.retry_if_exception_type(LLMTimeoutError)
| tenacity.retry_if_exception(_is_retriable_llm_api_error)
),
wait=tenacity.wait_exponential(multiplier=retry_delay, min=retry_delay, max=60),
stop=tenacity.stop_after_attempt(max_retries + 1),
wait=tenacity.wait_exponential(multiplier=retry_delay, min=retry_delay, max=120),
stop=tenacity.stop_after_attempt(max_retries + 2),
before_sleep=lambda retry_state: logger.warning(
f"LLM call failed (attempt {retry_state.attempt_number}/{max_retries + 1}), "
f"retrying in {retry_state.upcoming_sleep:.1f}s... Error: {str(retry_state.outcome.exception())}"
Expand Down